KeyError: 'query_tok' about nl2sql HOT 5 CLOSED

have you preprocess the data?

from nl2sql.

ub16hp@UB16HP:/ub16_prj/NL2SQL$ python extract_vocab.py
Loading from original dataset
Loading data from data/train_tok.jsonl
Traceback (most recent call last):
File "extract_vocab.py", line 21, in
load_dataset(0, use_small=USE_SMALL)
File "/home/ub16hp/ub16_prj/NL2SQL/sqlnet/utils.py", line 41, in load_dataset
'data/train_tok.tables.jsonl', use_small=use_small)
File "/home/ub16hp/ub16_prj/NL2SQL/sqlnet/utils.py", line 18, in load_data
with open(SQL_PATH) as inf:
IOError: [Errno 2] No such file or directory: 'data/train_tok.jsonl'
ub16hp@UB16HP:/ub16_prj/NL2SQL$

cannot find _tok in the data.tar.gz in wikisql

from nl2sql.

Can not read your post.

from nl2sql.

ub16hp@UB16HP:/ub16_prj/NL2SQL$ python extract_vocab.py
Loading from re-split dataset
Loading data from data/train.jsonl
Loading data from data/train.tables.jsonl
Loading data from data/dev.jsonl
Loading data from data/dev.tables.jsonl
Loading data from data/test.jsonl
Loading data from data/test.tables.jsonl
Loading word embedding from glove/glove.42B.300d.txt
Length of word vocabulary: 1917494
Traceback (most recent call last):
File "extract_vocab.py", line 39, in
for tok in sql['question_tok']:
KeyError: 'question_tok'
ub16hp@UB16HP:/ub16_prj/NL2SQL$

from nl2sql.

I figure it out.

from nl2sql.